The DRACO 16384\u00d7 MI300A AI Supercomputer is RDP’s flagship exascale HPC + AI supercomputer \u2014 16384 AMD Instinct MI300A APUs, the same accelerator architecture behind the world’s leadership-class FP64 systems, delivering ~2.1 PB unified HBM3 of unified accelerator memory in a full liquid-cooled data hall on a non-blocking InfiniBand spine. It is the largest converged simulation-and-AI machine RDP builds, engineered for national programmes \u2014 on-premises, in INR, on a GST invoice.<\/p>\n
Delivered as a single national engagement, RDP co-designs the reference architecture, integrates, cools and burns it in, and hands over one validated supercomputer with one warranty and one support contract. Its defining strength: FP64 HPC leadership and AI fused in one APU with unified CPU-GPU memory.<\/p>\n
This is the top of the HPC + foundation-model<\/strong> convergence: a flagship exascale supercomputer for both scientific simulation and frontier AI. With ~2.1 PB unified HBM3 of unified accelerator memory on a non-blocking fabric, it is sized to sustain<\/strong> national-scale HPC\/AI on-prem \u2014 the sovereign, owned alternative to hyperscale capacity.<\/p>\n We don’t publish inflated peak numbers. The honest picture: 16384 MI300A APUs (~2.1 PB unified HBM3) on a non-blocking fabric are sized for flagship exascale converged HPC + AI. Want certainty? Request a free benchmark \u2014 your HPC codes and AI models, including a scaling test \u2014 on a representative configuration before you commit<\/strong>; we’ll send back real performance and scaling efficiency.<\/p>\n At flagship exascale, owning is a sovereign and economic decision: an always-on hyperscale cloud system dominates any national budget over a multi-year horizon, while on-prem keeps sovereign data, codes and capability in-country. RDP pricing is fixed in INR with a GST input-credit-eligible invoice \u2014 ask for a multi-year TCO and financing model<\/strong>.<\/p>\n Ships pre-integrated and validated<\/strong>: AMD ROCm, HIP, RCCL, the InfiniBand stack, Slurm and\/or Kubernetes, with PyTorch (ROCm) and vLLM (ROCm) on a supported Linux LTS, plus monitoring and a scheduler. Optional managed operations and an HPC\/MLOps platform.<\/p>\n A full liquid-cooled exascale data hall with the highest power density in the range \u2014 RDP co-designs facility power, CDU\/manifold and water, the InfiniBand spine, floor layout and redundancy. (Exact power, BTU, flow and facility figures confirmed in the design package.)<\/em> Full out-of-band management across the data hall.<\/p>\n 14 years of Make-in-India infrastructure and 300,000+ devices shipped<\/strong>. Indian OEM, INR pricing, GST tax invoice (HSN 8471), pan-India onsite engineers, GeM availability, and DPDP \/ sovereign-AI-ready deployment.<\/p>\n This is RDP’s flagship exascale HPC + AI supercomputer, made to order \u2014 talk to an RDP solution architect<\/strong>, co-design the architecture for your codes and models, get a multi-year TCO and financing plan, and run a benchmark before you commit.<\/strong> Request a quote to begin.<\/p>\n","protected":false},"excerpt":{"rendered":" 16384\u00d7 MI300A \u00b7 Integrated AMD Zen4 (APU, per node) \u00b7 Unified APU memory (HBM3) \u00b7 256 PB parallel NVMe \u00b7 Data hall \u00b7 liquid-cooled<\/p>\n","protected":false},"featured_media":2131,"comment_status":"open","ping_status":"closed","template":"","meta":{"_yoast_wpseo_title":"","_yoast_wpseo_metadesc":"","rank_math_title":"DRACO 16384\u00d7 MI300A AI Supercomputer \u2014 ~2.1 PB unified HBM3, flagship exascale (ROCm) | RDP GPU Mart","rank_math_description":"RDP flagship exascale supercomputer \u2014 16384\u00d7 MI300A (~2.1 PB unified HBM3), AMD ROCm, FP64 HPC + frontier AI, non-blocking InfiniBand, liquid-cooled. Make-in-India, GST invoice. Request a quote.","_hermes_jsonld":""},"product_brand":[],"product_cat":[20],"product_tag":[],"class_list":["post-1826","product","type-product","status-publish","has-post-thumbnail","product_cat-supercomputers","pa_form-factor-rack","pa_gpu-model-amd-instinct-mi300a","pa_series-draco","pa_use-case-agentic-ai","pa_use-case-computer-vision","pa_use-case-generative-ai","pa_use-case-hpc-ai","pa_use-case-inference","pa_use-case-llm-training","pa_use-case-fine-tuning","pa_use-case-nlp-speech","pa_use-case-rag","pa_use-case-sovereign-ai","pa_workload-fit-flagship-exascale-supercomputer","first","instock","taxable","shipping-taxable","product-type-external"],"_links":{"self":[{"href":"https:\/\/rdp.in\/gpu-mart\/wp-json\/wp\/v2\/product\/1826","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/rdp.in\/gpu-mart\/wp-json\/wp\/v2\/product"}],"about":[{"href":"https:\/\/rdp.in\/gpu-mart\/wp-json\/wp\/v2\/types\/product"}],"replies":[{"embeddable":true,"href":"https:\/\/rdp.in\/gpu-mart\/wp-json\/wp\/v2\/comments?post=1826"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/rdp.in\/gpu-mart\/wp-json\/wp\/v2\/media\/2131"}],"wp:attachment":[{"href":"https:\/\/rdp.in\/gpu-mart\/wp-json\/wp\/v2\/media?parent=1826"}],"wp:term":[{"taxonomy":"product_brand","embeddable":true,"href":"https:\/\/rdp.in\/gpu-mart\/wp-json\/wp\/v2\/product_brand?post=1826"},{"taxonomy":"product_cat","embeddable":true,"href":"https:\/\/rdp.in\/gpu-mart\/wp-json\/wp\/v2\/product_cat?post=1826"},{"taxonomy":"product_tag","embeddable":true,"href":"https:\/\/rdp.in\/gpu-mart\/wp-json\/wp\/v2\/product_tag?post=1826"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}Industry use cases<\/h3>\n
\n
Performance \u2014 and how to be sure<\/h3>\n
Series & upgrade path<\/h3>\n
\n
On-prem vs cloud \u2014 the TCO case<\/h3>\n
Software & day-one readiness<\/h3>\n
Power, cooling & rack integration<\/h3>\n
Deployment, warranty & support<\/h3>\n
\n
Why RDP<\/h3>\n
Buy with confidence<\/h3>\n